New Approach Based on Texture and Geometric Features for Text Detection
Identifieur interne : 000700 ( Main/Exploration ); précédent : 000699; suivant : 000701New Approach Based on Texture and Geometric Features for Text Detection
Auteurs : Hinde Anoual [Maroc, France] ; Sanaa El Fkihi [Maroc] ; Abdelilah Jilbab [Maroc] ; Driss Aboutajdine [Maroc]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2010.
Abstract
Abstract: Due to the huge amount of data carried by images, it is very important to detect and identify the text region as accurately as possible before performing any character recognition. In this paper we describe a text detection algorithm in complex background. It is based on texture and connected components analysis. First we abstract texture regions which usually contain text. Second, we segment the texture regions into suitable objects; the image is segmented into three classes. Finally, we analyze all connected components present in each binary image according to the three classes with the aim to remove non-text regions. Experiments on a benchmark database show the advantages of the new proposed method compared to another one. Especially, our method is insensitive to complex background, font size and color; and offers high precision (83%) and recall(73%) as well.
Url:
DOI: 10.1007/978-3-642-13681-8_19
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001105
- to stream Istex, to step Curation: 001050
- to stream Istex, to step Checkpoint: 000280
- to stream Main, to step Merge: 000705
- to stream Main, to step Curation: 000700
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">New Approach Based on Texture and Geometric Features for Text Detection</title><author><name sortKey="Anoual, Hinde" sort="Anoual, Hinde" uniqKey="Anoual H" first="Hinde" last="Anoual">Hinde Anoual</name></author><author><name sortKey="El Fkihi, Sanaa" sort="El Fkihi, Sanaa" uniqKey="El Fkihi S" first="Sanaa" last="El Fkihi">Sanaa El Fkihi</name></author><author><name sortKey="Jilbab, Abdelilah" sort="Jilbab, Abdelilah" uniqKey="Jilbab A" first="Abdelilah" last="Jilbab">Abdelilah Jilbab</name></author><author><name sortKey="Aboutajdine, Driss" sort="Aboutajdine, Driss" uniqKey="Aboutajdine D" first="Driss" last="Aboutajdine">Driss Aboutajdine</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:7F42DDFBEB21B8C8C3CAB8E2745CF9588892B770</idno><date when="2010" year="2010">2010</date><idno type="doi">10.1007/978-3-642-13681-8_19</idno><idno type="url">https://api.istex.fr/document/7F42DDFBEB21B8C8C3CAB8E2745CF9588892B770/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001105</idno><idno type="wicri:Area/Istex/Curation">001050</idno><idno type="wicri:Area/Istex/Checkpoint">000280</idno><idno type="wicri:doubleKey">0302-9743:2010:Anoual H:new:approach:based</idno><idno type="wicri:Area/Main/Merge">000705</idno><idno type="wicri:Area/Main/Curation">000700</idno><idno type="wicri:Area/Main/Exploration">000700</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">New Approach Based on Texture and Geometric Features for Text Detection</title><author><name sortKey="Anoual, Hinde" sort="Anoual, Hinde" uniqKey="Anoual H" first="Hinde" last="Anoual">Hinde Anoual</name><affiliation wicri:level="1"><country xml:lang="fr">Maroc</country><wicri:regionArea>LRIT, unité associée au CNRST, FSR, Mohammed V University Agdal</wicri:regionArea><wicri:noRegion>Mohammed V University Agdal</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">France</country></affiliation></author><author><name sortKey="El Fkihi, Sanaa" sort="El Fkihi, Sanaa" uniqKey="El Fkihi S" first="Sanaa" last="El Fkihi">Sanaa El Fkihi</name><affiliation wicri:level="1"><country xml:lang="fr">Maroc</country><wicri:regionArea>LRIT, unité associée au CNRST, FSR, Mohammed V University Agdal</wicri:regionArea><wicri:noRegion>Mohammed V University Agdal</wicri:noRegion></affiliation><affiliation wicri:level="1"><country xml:lang="fr">Maroc</country><wicri:regionArea>ENSIAS, Mohammed V University Soussi, BP 713, Rabat</wicri:regionArea><wicri:noRegion>Rabat</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Maroc</country></affiliation></author><author><name sortKey="Jilbab, Abdelilah" sort="Jilbab, Abdelilah" uniqKey="Jilbab A" first="Abdelilah" last="Jilbab">Abdelilah Jilbab</name><affiliation wicri:level="1"><country xml:lang="fr">Maroc</country><wicri:regionArea>LRIT, unité associée au CNRST, FSR, Mohammed V University Agdal</wicri:regionArea><wicri:noRegion>Mohammed V University Agdal</wicri:noRegion></affiliation><affiliation wicri:level="1"><country xml:lang="fr">Maroc</country><wicri:regionArea>Rabat-Instituts, ENSET, Madinat AL Irfane, B.P 6207, Rabat</wicri:regionArea><wicri:noRegion>Rabat</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Maroc</country></affiliation></author><author><name sortKey="Aboutajdine, Driss" sort="Aboutajdine, Driss" uniqKey="Aboutajdine D" first="Driss" last="Aboutajdine">Driss Aboutajdine</name><affiliation wicri:level="1"><country xml:lang="fr">Maroc</country><wicri:regionArea>LRIT, unité associée au CNRST, FSR, Mohammed V University Agdal</wicri:regionArea><wicri:noRegion>Mohammed V University Agdal</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Maroc</country></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2010</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">7F42DDFBEB21B8C8C3CAB8E2745CF9588892B770</idno><idno type="DOI">10.1007/978-3-642-13681-8_19</idno><idno type="ChapterID">19</idno><idno type="ChapterID">Chap19</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: Due to the huge amount of data carried by images, it is very important to detect and identify the text region as accurately as possible before performing any character recognition. In this paper we describe a text detection algorithm in complex background. It is based on texture and connected components analysis. First we abstract texture regions which usually contain text. Second, we segment the texture regions into suitable objects; the image is segmented into three classes. Finally, we analyze all connected components present in each binary image according to the three classes with the aim to remove non-text regions. Experiments on a benchmark database show the advantages of the new proposed method compared to another one. Especially, our method is insensitive to complex background, font size and color; and offers high precision (83%) and recall(73%) as well.</div></front></TEI><affiliations><list><country><li>France</li><li>Maroc</li></country></list><tree><country name="Maroc"><noRegion><name sortKey="Anoual, Hinde" sort="Anoual, Hinde" uniqKey="Anoual H" first="Hinde" last="Anoual">Hinde Anoual</name></noRegion><name sortKey="Aboutajdine, Driss" sort="Aboutajdine, Driss" uniqKey="Aboutajdine D" first="Driss" last="Aboutajdine">Driss Aboutajdine</name><name sortKey="Aboutajdine, Driss" sort="Aboutajdine, Driss" uniqKey="Aboutajdine D" first="Driss" last="Aboutajdine">Driss Aboutajdine</name><name sortKey="El Fkihi, Sanaa" sort="El Fkihi, Sanaa" uniqKey="El Fkihi S" first="Sanaa" last="El Fkihi">Sanaa El Fkihi</name><name sortKey="El Fkihi, Sanaa" sort="El Fkihi, Sanaa" uniqKey="El Fkihi S" first="Sanaa" last="El Fkihi">Sanaa El Fkihi</name><name sortKey="El Fkihi, Sanaa" sort="El Fkihi, Sanaa" uniqKey="El Fkihi S" first="Sanaa" last="El Fkihi">Sanaa El Fkihi</name><name sortKey="Jilbab, Abdelilah" sort="Jilbab, Abdelilah" uniqKey="Jilbab A" first="Abdelilah" last="Jilbab">Abdelilah Jilbab</name><name sortKey="Jilbab, Abdelilah" sort="Jilbab, Abdelilah" uniqKey="Jilbab A" first="Abdelilah" last="Jilbab">Abdelilah Jilbab</name><name sortKey="Jilbab, Abdelilah" sort="Jilbab, Abdelilah" uniqKey="Jilbab A" first="Abdelilah" last="Jilbab">Abdelilah Jilbab</name></country><country name="France"><noRegion><name sortKey="Anoual, Hinde" sort="Anoual, Hinde" uniqKey="Anoual H" first="Hinde" last="Anoual">Hinde Anoual</name></noRegion></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000700 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000700 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:7F42DDFBEB21B8C8C3CAB8E2745CF9588892B770
|texte= New Approach Based on Texture and Geometric Features for Text Detection
}}
| This area was generated with Dilib version V0.6.32. |  |